The project is a collaboration with Magneti Marelli for the implementation of a Road Sign Recognition system for any vehicle and a Start Inhibit system for heavy goods vehicles.

Traffic Sign Recognition

The road signs detection and classification system is based on a three-step algorithm composed of color segmentation, shape recognition, and a neural network. The final goal of this algorithm is to detect and classify almost all road signs present along Italian roads.
Color segmentation was suggested by the aim to achieve real time execution, since color-based segmentation is faster than the one based on shape. In order to save computational time, only the RGB color space, directly supplied by the chosen camera, or color spaces that can be obtained with linear transformations, are considered.
Two different methods are used for shape detection, one is based on pattern matching with simple models and the other one is based on edge detection and geometrical cues.
The complete set of signs taken in account has been divided in several categories according to their shape and color. Finally for each road signs set a neural network is built and trained.

==> See Magneti Marelli Web Page on this project.

Start Inhibit

Problems concerning traffic mobility, safety, and energy consumption have become more serious in most developed countries in recent years. The endeavors to solve these problems have triggered the interest towards new fields of research and applications, such as Advanced Driving Assistance Systems.

In particular, concerning heavy goods vehicles (HGVs), many accidents involving trucks are related to the limited field of view of the driver: there are large blind spots all around the vehicle. Some of these blind areas can be at least partly covered by additional mirrors. However, this is not always an optimal solution considering the aerodynamic effects and also the resulting complex driver interface. The most effective single measure would be to improve the forward vision from HGV cabs so that an average size pedestrian could be seen even when standing right up against the front of the vehicle. This would have been likely to save the lives of 12% of the pedestrians killed by HGVs. Changing the design of the front of a truck in this way is not an easy task. Similar benefits can be achieved by using sensors to detect the presence of a pedestrian or an obstacle and to warn the driver and also to prevent the vehicle from taking off when something is present in the forward blind spot: this is called start-inhibit.

From this system is derived VOD, our powerful close range obstacle detector.

==> See Magneti Marelli Web Page on this project.